© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123058
    Prev
    Next
    INDEX
    Explanations

    wherein

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _right
    -0.07
    gui
    -0.06
    ResourceId
    -0.06
    append
    -0.06
    'ai
    -0.06
    Pod
    -0.06
     remake
    -0.06
     scape
    -0.06
     squad
    -0.06
    km
    -0.06
    POSITIVE LOGITS
     ByVal
    0.12
    @synthesize
    0.11
     wherein
    0.11
    @property
    0.11
     PropTypes
    0.10
    synthesize
    0.08
    WithOptions
    0.07
     linen
    0.07
    DllImport
    0.07
     zosta
    0.07
    Activations Density 0.004%

    No Known Activations